R Notebook

library(devtools) library(flexdashboard) library(lubridate) library(dplyr) library(ggplot2) library(ggstance) library(ggalt) library(viridisLite)

ggplot(data = fatal_police_shootings_data, aes(y = race)) + 
        geom_bar(aes(fill = ..count..)) +
        theme_minimal(base_size = 13) +
        theme(legend.position = "none") +
        scale_x_continuous(expand=c(0,0)) +
        scale_fill_gradient(low = "royalblue3", high = "navyblue") +
        labs(y = NULL, x = "Number of deaths")

stateinfo <- fatal_police_shootings_data %>% group_by(state) %>% dplyr::summarise(n = n()) %>% 
        dplyr::arrange(desc(n)) %>% top_n(15) %>% 
        mutate(state = factor(state, levels = rev(unique(state))))

Selecting by n

ggplot(stateinfo, aes(x = n, y = state)) +
        geom_bar(stat="identity", aes(fill = n)) +
        geom_text(aes(x = 17, y = state, label=as.character(state)), color="white", size=4) +
        labs(y = NULL, x = "Number of deaths") +
        scale_fill_gradient(low = "grey",
  high = "orange",space = "rgb",
  na.value = "grey50", guide = "colourbar") +
        theme_minimal(base_size = 13) +
        theme(axis.text.y=element_blank()) +
        theme(legend.position = "none") +
        scale_x_continuous(expand=c(0,0))

Warning: Non Lab interpolation is deprecated

levels(fatal_police_shootings_data$gender) <- c("Female", "Male")
levels(fatal_police_shootings_data$race) <- c("Unknown", "Asian", "Black", "Hispanic", "Other", "White")

ggplot(data = knownraced, aes(y = race)) + 
        geom_bar(aes(fill = ..count..)) +
    geom_vline(xintercept = 2500, linetype = 2, colour = "grey20") +
  geom_text(x = 2500, y = 4, label = "majority of\nvictims", 
            hjust = 0, size = 11 * 0.8 / .pt, colour = "grey20") +
  scale_x_continuous(expand = expansion(mult = c(0, 0.1))) +
  scale_y_discrete(limits = rev) +
        theme_minimal(base_size = 13) +
        theme(legend.position = "none") +
        scale_x_continuous(expand=c(0,0)) +
        scale_colour_manual(breaks = c("W", "NA", "O", "B", "A", "H","N"),
                      values = c("NavyBlue", "darkred", "grey","brown", "yellow","darkgreen" , "darkred")) +
        labs(y = NULL, x = "Total of Shootings")

Scale for 'x' is already present. Adding another scale for 'x', which will replace the
existing scale.

ggplot(data = fatal_police_shootings_data, aes(x = age)) + 
        geom_density(fill="#69b3a2", color="#e9ecef",adjust=1.5, alpha=0.4) +
        theme_minimal(base_size = 13) +
        theme(legend.position = "none") +
        scale_x_continuous(expand=c(0,0)) +
        scale_fill_gradient(low = "white", high = "navyblue") +
        labs(x = "Age at death", y = "Density")

Warning: Removed 384 rows containing non-finite values
(stat_density).

armedinfo <- fatal_police_shootings_data %>% group_by(armed) %>% dplyr::summarise(n = n()) %>% 
        arrange(desc(n)) %>% top_n(10) %>% 
        mutate(armed = factor(armed, levels = rev(unique(armed))))

Selecting by n

ggplot(data = armedinfo, aes(x = n, y = armed)) + 
        geom_bar(stat="identity", aes(fill = n)) +
        theme_minimal(base_size = 13) +
        theme(legend.position = "none") +
        scale_x_continuous(expand=c(0,0)) +
        scale_fill_gradient(low = "royalblue3", high = "navyblue") +
        labs(y = NULL, x = "Number of deaths")

genderinfo <- fatal_police_shootings_data %>% group_by(gender) %>% dplyr::summarise(n = n()) 

ggplot(data = genderinfo, aes(x = n, y = gender)) + 
        geom_bar(stat="identity", aes(fill = n)) +
        theme_minimal(base_size = 13) +
        theme(legend.position = "none") +
        scale_x_continuous(expand=c(0,0)) +
        scale_fill_gradient(low = "white", high = "darkgreen") +
        labs(y = NULL, x = "Gender")

mybreaks <- c(0.02, 0.04, 0.08, 1, 7)

data <- fatal_police_shootings_data %>% group_by(fatal_police_shootings_data$state) %>% dplyr::summarise(n = n()) %>% 
        dplyr::arrange(desc(n))

fatal_police_shootings_data %>%
  ggplot() +
    geom_polygon(data = fatal_police_shootings_data, aes(x=fatal_police_shootings_data$longitude, y = fatal_police_shootings_data$latitude), fill="grey", alpha=0.3) +
    geom_point(  aes(x=fatal_police_shootings_data$longitude, y=fatal_police_shootings_data$latitude , size = after_stat(n)), shape=20, stroke=FALSE) +
    scale_size_continuous(name="Shootings Total", range=c(1,1100), breaks=mybreaks) +
    scale_alpha_continuous(name="Shootings Total", range=c(0.1, .9), breaks=mybreaks) +
    scale_color_viridis(option="magma", trans="log", breaks=mybreaks, name="Shootings Total" ) +
    theme_void() + ylim(50,59) + coord_map() + 
    guides( colour = guide_legend()) +
    ggtitle("Shootings Distribution accros the US") +
    theme(
      legend.position = c(0.85, 0.8),
      text = element_text(color = "#22211d"),
      plot.background = element_rect(fill = "#f5f5f2", color = NA), 
      panel.background = element_rect(fill = "#f5f5f2", color = NA), 
      legend.background = element_rect(fill = "#f5f5f2", color = NA),
      plot.title = element_text(size= 16, hjust=0.1, color = "#4e4d47", margin = margin(b = -0.1, t = 0.4, l = 2, unit = "cm")),
    )

Error: Aesthetics must be valid computed stats. Problematic aesthetic(s): size = after_stat(n). 
Did you map your stat in the wrong layer?
Run `rlang::last_error()` to see where the error occurred.

ggplot(data = fatal_police_shootings_data, aes(y = manner_of_death)) + 
        geom_bar(aes(fill = ..count..)) +
        theme_minimal(base_size = 13) +
        theme(legend.position = "none") +
        scale_x_continuous(expand=c(0,0)) +
        scale_fill_gradient(low = "grey", high = "darkred") +
        labs(y = NULL, x = "Number of deaths")

us_cont <- fatal_police_shootings_data[fatal_police_shootings_data$state]

Error: Can't subset columns that don't exist.
x Columns `WA`, `OR`, `KS`, `CA`, `CO`, etc. don't exist.
Run `rlang::last_error()` to see where the error occurred.

yearinfo <- fatal_police_shootings_data %>% group_by(year) %>% dplyr::summarise(n = n())

yearinfo %>% 
  ggplot(aes(x = year, y = n)) +
    geom_line( color="#69b3a2") +
    geom_point(shape=21, color="black", fill="#69b3a2", size=6) +theme_minimal(base_size = 13)+
    ggtitle("Rate of shootings remains steady")

fatal_police_shootings_data <- fatal_police_shootings_data %>%
  mutate(year = lubridate::year(date), 
         month = lubridate::month(date), 
         day = lubridate::day(date))

yearly <- fatal_police_shootings_data %>% group_by(year , month) %>% dplyr::summarise(n = n())

`summarise()` has grouped output by 'year'. You can override using the `.groups` argument.

yearly %>% 
  ggplot(aes(x= month , y = n , group = year , color = year))+
  geom_line(color="#69b3a2", size=1, alpha=0.9)+
  scale_color_viridis(discrete = TRUE)+
  ggtitle("Rate of Shootings remains steady (2015-2021)")+
  theme_minimal()+
  scale_colour_manual(name = "Year", 
                      values = c("green3", "orange", "blue", "red", "grey")+
  ylab("Total Shootings")

Error: Incomplete expression: yearly %>% 
  ggplot(aes(x= month , y = n , group = year , color = year))+
  geom_line(color="#69b3a2", size=1, alpha=0.9)+
  scale_color_viridis(discrete = TRUE)+
  ggtitle("Rate of Shootings remains steady (2015-2021)")+
  theme_minimal()+
  scale_colour_manual(name = "Year", 
                      values = c("green3", "orange", "blue", "red", "grey")+
  ylab("Total Shootings")

geom_point( data=aqi_map, aes(x=long, y=lat,color=mean_pollution,size=mean_pollution))

Error in fortify(data) : object 'aqi_map' not found

fatal_police_shootings_data%>%
  mutate(fatal_police_shootings_data, region = 
           ifelse(state=="CA"|state=="AZ"|state=="NM"|state=="CO"|state=="ID"|state=="OR"|
                    state=="WA"|state=="AK"|state=="HI", "West",
                  ifelse(state=="TX"|state=="OK"|state=="AR"|state=="LA"|state=="MS"|state=="AL"|
                           state=="TN"|state=="FL"|state=="GA"|state=="NC"|state=="SC"|state=="VA"|
                           state=="KY"|state=="MD"|state=="WV"|state=="DC","South",
                         ifelse(state=="KS"|state=="MO"|state=="IL"|state=="IN"|state=="OH"
                                |state=="IA"|state=="NE"|state=="SD"|state=="ND"|state=="MN"|
                                  state=="WI"|state=="MI","Midwest", "Northeast"))))

fatal_police_shootings_data %>%
summary(subset(fatal_police_shootings_data, region == "Midwest"))

       id           name                date            manner_of_death       armed          
 Min.   :   3   Length:7001        Min.   :2015-01-02   Length:7001        Length:7001       
 1st Qu.:1970   Class :character   1st Qu.:2016-10-12   Class :character   Class :character  
 Median :3883   Mode  :character   Median :2018-07-05   Mode  :character   Mode  :character  
 Mean   :3871                      Mean   :2018-07-16                                        
 3rd Qu.:5771                      3rd Qu.:2020-04-25                                        
 Max.   :7645                      Max.   :2021-12-31                                        
                                                                                             
      age           gender              race               city              state          
 Min.   : 6.00   Length:7001        Length:7001        Length:7001        Length:7001       
 1st Qu.:27.00   Class :character   Class :character   Class :character   Class :character  
 Median :35.00   Mode  :character   Mode  :character   Mode  :character   Mode  :character  
 Mean   :37.13                                                                              
 3rd Qu.:45.00                                                                              
 Max.   :92.00                                                                              
 NA's   :364                                                                                
 signs_of_mental_illness threat_level           flee           body_camera    
 Mode :logical           Length:7001        Length:7001        Mode :logical  
 FALSE:5451              Class :character   Class :character   FALSE:6025     
 TRUE :1550              Mode  :character   Mode  :character   TRUE :976      
                                                                              
                                                                              
                                                                              
                                                                              
   longitude          latitude     is_geocoding_exact      year          month       
 Min.   :-160.01   Min.   :19.50   Mode :logical      Min.   :2015   Min.   : 1.000  
 1st Qu.:-112.07   1st Qu.:33.48   FALSE:18           1st Qu.:2016   1st Qu.: 3.000  
 Median : -94.23   Median :36.10   TRUE :6983         Median :2018   Median : 6.000  
 Mean   : -97.11   Mean   :36.66                      Mean   :2018   Mean   : 6.439  
 3rd Qu.: -83.12   3rd Qu.:40.01                      3rd Qu.:2020   3rd Qu.:10.000  
 Max.   : -67.87   Max.   :71.30                      Max.   :2021   Max.   :12.000  
 NA's   :575       NA's   :575                                                       
      day       
 Min.   : 1.00  
 1st Qu.: 8.00  
 Median :16.00  
 Mean   :15.62  
 3rd Qu.:23.00  
 Max.   :31.00  
                

blacks= fatal_police_shootings_data[fatal_police_shootings_data$race=="B",]

Warning message:
In makeContext(x) : reached elapsed time limit

whites= fatal_police_shootings_data[fatal_police_shootings_data$race=="W",]
hisLats= fatal_police_shootings_data[fatal_police_shootings_data$race=="H",]
summary(blacks)

       id           name                date            manner_of_death   
 Min.   :  17   Length:2665        Min.   :2015-01-06   Length:2665       
 1st Qu.:1726   Class :character   1st Qu.:2016-07-11   Class :character  
 Median :3595   Mode  :character   Median :2018-04-05   Mode  :character  
 Mean   :3586                      Mean   :2018-04-12                     
 3rd Qu.:5350                      3rd Qu.:2019-12-19                     
 Max.   :7645                      Max.   :2021-12-30                     
 NA's   :1082                      NA's   :1082                           
    armed                age           gender              race          
 Length:2665        Min.   :13.00   Length:2665        Length:2665       
 Class :character   1st Qu.:24.00   Class :character   Class :character  
 Mode  :character   Median :31.00   Mode  :character   Mode  :character  
                    Mean   :32.73                                        
                    3rd Qu.:39.00                                        
                    Max.   :88.00                                        
                    NA's   :1113                                         
     city              state           signs_of_mental_illness
 Length:2665        Length:2665        Mode :logical          
 Class :character   Class :character   FALSE:1337             
 Mode  :character   Mode  :character   TRUE :246              
                                       NA's :1082             
                                                              
                                                              
                                                              
 threat_level           flee           body_camera       longitude      
 Length:2665        Length:2665        Mode :logical   Min.   :-157.85  
 Class :character   Class :character   FALSE:1278      1st Qu.: -95.49  
 Mode  :character   Mode  :character   TRUE :305       Median : -87.21  
                                       NA's :1082      Mean   : -90.76  
                                                       3rd Qu.: -80.61  
                                                       Max.   : -70.28  
                                                       NA's   :1170     
    latitude     is_geocoding_exact      year          month       
 Min.   :20.89   Mode :logical      Min.   :2015   Min.   : 1.000  
 1st Qu.:32.95   FALSE:2            1st Qu.:2016   1st Qu.: 3.000  
 Median :36.18   TRUE :1581         Median :2018   Median : 6.000  
 Mean   :36.29   NA's :1082         Mean   :2018   Mean   : 6.244  
 3rd Qu.:39.96                      3rd Qu.:2019   3rd Qu.: 9.000  
 Max.   :61.58                      Max.   :2021   Max.   :12.000  
 NA's   :1170                       NA's   :1082   NA's   :1082    
      day       
 Min.   : 1.00  
 1st Qu.: 8.00  
 Median :15.00  
 Mean   :15.51  
 3rd Qu.:23.00  
 Max.   :31.00  
 NA's   :1082   

summary(whites)

       id           name                date            manner_of_death   
 Min.   :   4   Length:4087        Min.   :2015-01-02   Length:4087       
 1st Qu.:1696   Class :character   1st Qu.:2016-07-03   Class :character  
 Median :3438   Mode  :character   Median :2018-02-17   Mode  :character  
 Mean   :3488                      Mean   :2018-03-09                     
 3rd Qu.:5298                      3rd Qu.:2019-11-26                     
 Max.   :7641                      Max.   :2021-12-26                     
 NA's   :1082                      NA's   :1082                           
    armed                age          gender              race          
 Length:4087        Min.   : 6     Length:4087        Length:4087       
 Class :character   1st Qu.:30     Class :character   Class :character  
 Mode  :character   Median :38     Mode  :character   Mode  :character  
                    Mean   :40                                          
                    3rd Qu.:49                                          
                    Max.   :91                                          
                    NA's   :1129                                        
     city              state           signs_of_mental_illness
 Length:4087        Length:4087        Mode :logical          
 Class :character   Class :character   FALSE:2130             
 Mode  :character   Mode  :character   TRUE :875              
                                       NA's :1082             
                                                              
                                                              
                                                              
 threat_level           flee           body_camera       longitude      
 Length:4087        Length:4087        Mode :logical   Min.   :-158.02  
 Class :character   Class :character   FALSE:2682      1st Qu.:-107.59  
 Mode  :character   Mode  :character   TRUE :323       Median : -91.61  
                                       NA's :1082      Mean   : -95.37  
                                                       3rd Qu.: -82.73  
                                                       Max.   : -68.03  
                                                       NA's   :1252     
    latitude     is_geocoding_exact      year          month      
 Min.   :21.28   Mode :logical      Min.   :2015   Min.   : 1.00  
 1st Qu.:33.77   FALSE:4            1st Qu.:2016   1st Qu.: 3.00  
 Median :36.87   TRUE :3001         Median :2018   Median : 6.00  
 Mean   :37.39   NA's :1082         Mean   :2018   Mean   : 6.17  
 3rd Qu.:40.68                      3rd Qu.:2019   3rd Qu.: 9.00  
 Max.   :64.86                      Max.   :2021   Max.   :12.00  
 NA's   :1252                       NA's   :1082   NA's   :1082   
      day       
 Min.   : 1.00  
 1st Qu.: 8.00  
 Median :15.00  
 Mean   :15.44  
 3rd Qu.:23.00  
 Max.   :31.00  
 NA's   :1082   

summary(hisLats)

       id           name                date            manner_of_death   
 Min.   :   5   Length:2169        Min.   :2015-01-03   Length:2169       
 1st Qu.:1782   Class :character   1st Qu.:2016-08-08   Class :character  
 Median :3455   Mode  :character   Median :2018-02-25   Mode  :character  
 Mean   :3481                      Mean   :2018-03-07                     
 3rd Qu.:5094                      3rd Qu.:2019-09-18                     
 Max.   :7600                      Max.   :2021-12-26                     
 NA's   :1082                      NA's   :1082                           
    armed                age           gender              race          
 Length:2169        Min.   :13.00   Length:2169        Length:2169       
 Class :character   1st Qu.:26.00   Class :character   Class :character  
 Mode  :character   Median :33.00   Mode  :character   Mode  :character  
                    Mean   :33.72                                        
                    3rd Qu.:40.00                                        
                    Max.   :80.00                                        
                    NA's   :1111                                         
     city              state           signs_of_mental_illness
 Length:2169        Length:2169        Mode :logical          
 Class :character   Class :character   FALSE:897              
 Mode  :character   Mode  :character   TRUE :190              
                                       NA's :1082             
                                                              
                                                              
                                                              
 threat_level           flee           body_camera       longitude      
 Length:2169        Length:2169        Mode :logical   Min.   :-157.88  
 Class :character   Class :character   FALSE:925       1st Qu.:-118.19  
 Mode  :character   Mode  :character   TRUE :162       Median :-111.00  
                                       NA's :1082      Mean   :-106.26  
                                                       3rd Qu.: -97.51  
                                                       Max.   : -70.79  
                                                       NA's   :1123     
    latitude     is_geocoding_exact      year          month       
 Min.   :21.32   Mode :logical      Min.   :2015   Min.   : 1.000  
 1st Qu.:32.82   FALSE:2            1st Qu.:2016   1st Qu.: 3.000  
 Median :34.09   TRUE :1085         Median :2018   Median : 6.000  
 Mean   :34.96   NA's :1082         Mean   :2018   Mean   : 6.159  
 3rd Qu.:37.61                      3rd Qu.:2019   3rd Qu.: 9.000  
 Max.   :48.75                      Max.   :2021   Max.   :12.000  
 NA's   :1123                       NA's   :1082   NA's   :1082    
      day       
 Min.   : 1.00  
 1st Qu.: 8.00  
 Median :16.00  
 Mean   :15.74  
 3rd Qu.:23.00  
 Max.   :31.00  
 NA's   :1082   

ggplot(fatal_police_shootings_data,aes(x=age)) + 
  geom_histogram(data=subset(fatal_police_shootings_data,race == 'B'),fill = "red", alpha = 0.2,binwidth = 1) +
  geom_histogram(data=subset(fatal_police_shootings_data,race == 'W'),fill = "blue", alpha = 0.2,binwidth = 1) +
  geom_histogram(data=subset(fatal_police_shootings_data,race == 'H'),fill = "yellow", alpha = 0.3,binwidth = 1)

Warning: Removed 31 rows containing non-finite values (stat_bin).
Warning: Removed 47 rows containing non-finite values (stat_bin).
Warning: Removed 29 rows containing non-finite values (stat_bin).

p1=ggplot(hisLats, aes(age))+ 
  geom_histogram(color="black",fill="pink",binwidth=1, alpha=0.8)+
  ggtitle("Individuals killed by age- Race/ethnicity: Hispanic/latino") + xlim(6, 87)
p2=ggplot(blacks, aes(age))+ 
  geom_histogram(color="black",fill="green",binwidth=1, alpha=0.3)+
  ggtitle("Individuals killed by age- Race/ethnicity: Black") + xlim(6, 87)
p3=ggplot(whites, aes(age))+ 
  geom_histogram(color="black",fill="pink",binwidth=1, alpha=0.3)+
  ggtitle("Individuals killed by age- Race/ethnicity: White") + xlim(6, 87)
g1 <- ggplotGrob(p1)

Warning: Removed 1111 rows containing non-finite values (stat_bin).
Warning: Removed 2 rows containing missing values (geom_bar).

g2 <- ggplotGrob(p2)

Warning: Removed 1114 rows containing non-finite values (stat_bin).
Warning: Removed 2 rows containing missing values (geom_bar).

g3 <- ggplotGrob(p3)

Warning: Removed 1131 rows containing non-finite values (stat_bin).
Warning: Removed 2 rows containing missing values (geom_bar).

g <- rbind(g1,g2, g3, size = "first")
g$widths <- unit.pmax(g1$widths,g2$widths, g3$widths)
grid.newpage()

grid.draw(g)

# Age break down with armed by region
ggplot(data=fatal_police_shootings_data,aes(x=fatal_police_shootings_data$region,y=age,  fill=armed ))+
  geom_boxplot(outlier.colour="Black",  outlier.size=1, notch=FALSE)+
  labs(x='Race/Ethnicity', y= 'Age')+
  ggtitle("Age and 'armed' status of deceased by region")

Warning: Unknown or uninitialised column: `region`.
Warning: Unknown or uninitialised column: `region`.
Warning: Removed 364 rows containing non-finite values (stat_boxplot).

# Age break down with classification/cause of death by region
ggplot(data=fatal_police_shootings_data,aes(x=fatal_police_shootings_data$region,y=age,  fill=manner_of_death ))+
  geom_boxplot(outlier.colour="Black",  outlier.size=1, notch=FALSE)+
  labs(x='Race/Ethnicity', y= 'Age')+
  ggtitle("Age and cause of death")

Warning: Unknown or uninitialised column: `region`.
Warning: Unknown or uninitialised column: `region`.
Warning: Removed 364 rows containing non-finite values (stat_boxplot).

# Age breakdown with race by region
ggplot(data=fatal_police_shootings_data,aes(x=fatal_police_shootings_data$region,y=age,  fill=race))+
  geom_boxplot(outlier.colour="Black",  outlier.size=1, notch=FALSE)+
  labs(x='Region', y= 'Age')

Warning: Unknown or uninitialised column: `region`.
Warning: Unknown or uninitialised column: `region`.
Warning: Removed 364 rows containing non-finite values (stat_boxplot).

knownraced %>% group_by(race) %>% dplyr::summarise(n = n())

ggplot(knownraced,aes(race)) + 
  geom_bar(fill="royalblue") +
  ggtitle("Killings vs race/ethnicity of deceased")

library(tmap)

Warning: package ‘tmap’ was built under R version 4.1.2

library(tmaptools)

Warning: package ‘tmaptools’ was built under R version 4.1.2

shape <- read_sf("~/Assignment 1/USA_States_Generalized.shp")

{map_US + map_AL+ map_HI +  tm_shape(shootings_sf)+tm_dots(size= 0.1, col="race", title= "Race", id="name", popup.vars = c("Age:" = "age", "Gender:" = "gender","Date Killed:"="date", "Armed:"="armed","Fleeing:"="flee", "Signs of Mental Health Issues:" = "signs_of_mental_illness","Manner of Death: " = "manner_of_death","State:" = "state"))+
      tm_layout(title= "Map of Deadly Force US Police Shootings Jan 2015- December 2021",title.position = c('right', 'top'))+tmap_mode("view")}

tmap mode set to interactive viewing
legend.postion is used for plot mode. Use view.legend.position in tm_view to set the legend position in view mode.